I. Introduction and Background
Since the concept of artificial intelligence (AI) was proposed in the Dartmouth workshop, AI techniques have given rise to great reforms in various aspects of modern society, such as public opinion analysis in social media, recommender system of e-commerce and intelligent manufacturing in industrial production. In the whole AI community, artificial neural network (ANN) is one class of the most critical algorithms with profound influence. Unlike general networks [1], [2], ANN consists of many connected artificial neurons that model the function of biological neurons. These artificial neurons transmit nonlinear activation through some weighted connections. Then, the network can approximate a specific complicated function via stacking enough such transmission. Despite the significant achievements of ANNs, they are limited to their capacity of tackling data in the raw form [3]. Sophisticated feature engineering requiring considerable expertise is necessary for the network to learn reliable patterns from the raw data. Inspired by the investigations to hierarchical structures of human speech system, some novel network architectures with multiple layers are developed, namely deep neural networks (DNNs). These hierarchical neural architectures are expected to overcome the limitation of conventional ANNs.